Accuracy Improvement of Face Recognition System based on Co-occurrence Matrix of Local Median Binary Pattern
Rana Jelokhani Niaraki, Asadollah Shahbahrami · 2019
Face recognition is an important subject because of its usefulness in many applications like banking system and door access control systems. For this reason, there is always the need to recognize faces automatically with high accuracy. In this paper, we improve the accuracy of face recognition systems using Co-occurrence Matrix of Local Median Binary Pattern features. In other words, the combination of two algorithms is used. That way local median binary pattern (LMBP) operator applied on the image and then the co-occurrence matrix of the LMBP image is calculated. Our experimental results on ORL and Yale databases show that the proposed algorithm has the accuracy of 96.25% and 100% on mentioned image databases, respectively.